Loading the registry…
Model Context Protocol (MCP) servers for integrating with Claude Code
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
2 critical findings reported by agent-audit-kit, 1 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/kaar/mcp-servers, 18 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- mcp-servers
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
3 findings · 9.5s
v0.3.74
15 findings · 1.1s
v0.1.0
0 findings · 4.4s
v0.1.0
0 findings · 4.4s
v0.1.0
0 findings · 8.9s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 19, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 18 findings across every scanner that examined this package. 1 of 2 findings rated critical by their scanner was among the dismissals.
Not reviewed is not the same as clean. Those 3 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
5 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-AGENT-TRUST-002, AAK-AGENT-TRUST-001, AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/claude.yml, .github/workflows/claude-code-review.yml · reported by agent-audit-kit
2 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: TOOL_ABUSE_UNDECLARED_NETWORK, AAK-AGENT-001 · Files: /repo/repo/CLAUDE.md, CLAUDE.md · reported by cisco-skill-scanner, agent-audit-kit
The model could have called any of these a false positive and did not.
1 AAK-DNS-REBIND-002
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-LOGINJ-001
Files: src/mcp_servers/claude_docs_mcp.py · reported by agent-audit-kit
1 AAK-MCP-006
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-ENV-PLACEHOLDER-EXFIL-001
Files: src/mcp_servers/claude_docs_mcp.py · reported by agent-audit-kit
1 AAK-MCP-SDK-CVE-2026-52869-001
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
3 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SEC-MD-001, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: SECURITY.md, /repo/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
Critical risks: environment variable exfiltration and DNS rebinding.
The artifact presents a critical risk due to a finding (AAK-MCP-ENV-PLACEHOLDER-EXFIL-001) that could exfiltrate environment variables from `src/mcp_servers/claude_docs_mcp.py`. High severity findings also indicate a DNS rebinding vulnerability (AAK-DNS-REBIND-002) and a known SDK vulnerability (AAK-MCP-SDK-CVE-2026-52869-001), both located in `pyproject.toml`. These findings collectively point to potential for sensitive data exposure and network control issues.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit